TY - JOUR
T1 - Modeling Plasma Fabric Surface Treatment Using Fuzzy Logic and Artificial Neural Networks
AU - Radhia Abd Jelil , Xianyi Zeng Ludovic Koehl and Anne Perwuelz
JO - Journal of Information and Computing Science
VL - 2
SP - 141
EP - 152
PY - 2024
DA - 2024/01
SN - 8
DO - http://doi.org/
UR - https://global-sci.org/intro/article_detail/jics/22623.html
KW - neural networks, fuzzy selection criterion, modelling, atmospheric plasma, woven fabric 

AB -  In  this  paper,  Artificial  Neural  Networks  (ANNs)  are  used  to  model  the  effect  of  atmospheric 
air-plasma  treatment  on  fabric  surfaces  with  various  structures.  In  order  to  reduce  the  complexity  of  the 
models  and  increase  the  knowledge  and  comprehension  of  the  underlying  process,  a  fuzzy  sensitivity 
variation  criterion  is  used  to  select  the  most  relevant  parameters  which  are  taken  as  inputs  of  the  reduced 
neural  models.  The  model  outputs  are  the  water  contact  angle  and  the  capillarity  of  woven  fabrics, 
characterizing the change of fabric surfaces. The early stopping and Bayesian regularization techniques are 
used for improving the network’s generalization capability. Two different network configurations are studied. 
One  deals  with  two  networks  having  each  one  output  layer  neuron  and  another  with  a  single  network 
combining the two outputs. Obtained results showed that the first configuration combined with the Bayesian 
regularization approach is the most suitable to achieve a good prediction accuracy.